[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77PM20XVT8MQ5EDMMCSKDTG":3,"skill-same:01M77PM20XVT8MQ5EDMMCSKDTG":44},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M77PM20XVT8MQ5EDMMCSKDTG","loop-engineering",null,"Run the repository's end-to-end delivery loop from idea or legacy-project audit to plan, implementation, verification, documentation, and release preparation. Use when the user wants structured interactive guidance followed by persistent execution with minimal unnecessary stops.","NoMoneyDaddy\u002Fdemo-app","NoMoneyDaddy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F946647?v=4","01M77PJJ23FPSZHY6EBK1ZDHFS","奶爸","01M77PJJ2T4WRV1JT38TVP5WZK",0,"MIT","https:\u002F\u002Fgithub.com\u002FNoMoneyDaddy\u002Fdemo-app\u002Fblob\u002Fclaude\u002Fone-button-done-project-8xz5ky\u002F.agents\u002Fskills\u002Floop-engineering\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: loop-engineering\ndescription: Run the repository's end-to-end delivery loop from idea or legacy-project audit to plan, implementation, verification, documentation, and release preparation. Use when the user wants structured interactive guidance followed by persistent execution with minimal unnecessary stops.\n---\n\n# loop-engineering\n\n本 skill 是專案主工作流。\n\n## 讀取順序\n\n1. `AGENTS.md`\n2. `docs\u002Fsession_loop_contract.md`\n3. `docs\u002Finteractive_project_flow.md`\n4. `docs\u002Fproject_architecture_best_practices.md`\n5. `docs\u002Fproject_lifecycle_automation.md`\n6. `docs\u002Fsubagent_dispatch.md`\n\n## 兩種模式\n\n### A. 新專案\n\n1. 必要時先用 `interview-me`\n2. 用 `idea-refine` 收斂想法\n3. 用 `spec-driven-development` 建 spec\n4. 技術棧定了就先用 `project-config-generation`\n5. 用 `planning-and-task-breakdown` 切 task\n6. 再進實作 loop\n\n### B. 舊專案改善\n\n1. 先看入口檔、設定、測試、部署\n2. 先提改善與重構切片\n3. 使用者確認後才做大改\n\n## 預設流程\n\n這是預設路徑，不是固定步數。\n\n1. 先判斷現在是新專案還是舊專案\n2. 只問 1-3 組決策題\n3. 先跑 `node scripts\u002Finspect_agent_capabilities.js`\n4. 先讀：\n   - `docs\u002Floop_maturity_model.md`\n   - `docs\u002Fengineering_phase_loop.md`\n   - `docs\u002Floop_circuit_breaker.md`\n5. 根據情境讀：\n   - `prompts\u002Finteractive_tech_stack_prompt.md`\n   - `prompts\u002Finteractive_api_key_prompt.md`\n   - `prompts\u002Flegacy_project_improvement_prompt.md`\n6. 若缺 `.loop\u002F*`，先用 `goal-loop` 或 `node scripts\u002Finit_session_loop.js . --goal \"\u003Cobjective>\"`\n7. 技術棧確認後，先用 `project-config-generation` 落設定檔\n8. 先給短版方案\n9. 視任務大小決定：\n   - 小任務：直接切 task 開工\n   - 中大型任務：再補完整計畫與 task 切片\n10. 完成必要確認後，進入 build-test-fix-doc loop\n11. 每輪記錄 `maturity_level`、`retry_count`、`blocked_reason`、`convergence_state`\n12. 若是 JS \u002F TS 專案且有 Biome，啟用 quality loop：\n    - `npx @biomejs\u002Fbiome check --write \u003Cchanged-paths>`\n    - 必要時再跑測試\n13. 進 merge \u002F ship 前補：\n    - `code-review-and-quality`\n    - `observability-and-instrumentation`\n    - `shipping-and-launch`\n\n## 初始化\n\n若是新專案或缺少核心檔案，先執行：\n\n```bash\nnode scripts\u002Finit_project_workspace.js \u003CtargetDir> --name \u003CprojectName> --idea \"\u003Cidea>\"\n```\n\n再依情境推薦 skills \u002F tools：\n\n```bash\nnode scripts\u002Fauto_skill_setup.js --project-type \u003Ctype> --ui-style \u003Cstyle> --deployment \u003Ctarget> --language \u003Clang> --database \u003Cdb>\n```\n\n## 實作 loop\n\n每輪都做：\n\n1. 選一個最小 task\n2. 最小必要修改\n3. 跑對應驗證\n4. 失敗就修根因\n5. 看 circuit breaker 是否該停\n6. 更新：\n   - `.loop\u002FPLAN.md`\n   - `.loop\u002FSTATE.json`\n   - `.loop\u002FCHECKPOINTS.md`\n   - `.loop\u002FEVIDENCE.md`\n   - 必要時記 `tier`、`orientation`、`time_budget`\n7. 若流程穩定可重用，參考 `docs\u002Fskill_crystallization_loop.md`\n8. 更新：\n   - `docs\u002FTASKS.md`\n   - `docs\u002FDEBUG_NOTES.md`\n   - `docs\u002FSTATE.md`\n   - `README.md`\n\n## 技能路由\n\n- 想法模糊：`idea-refine`\n- 要 `\u002Fgoal` 類跨平台 loop：`goal-loop`\n- 缺 spec：`spec-driven-development`\n- 工作太大：`planning-and-task-breakdown`\n- 技術棧已定但設定檔未落地：`project-config-generation`\n- 開始實作：`incremental-implementation`\n- 行為變動：`test-driven-development`\n- framework 問題：`source-driven-development`\n- 前端：`frontend-ui-engineering`\n- API 邊界：`api-and-interface-design`\n- runtime 驗證：`browser-testing-with-devtools`\n- 除錯：`debugging-and-error-recovery`\n- JS \u002F TS 品質 loop：`biome-quality-automation`\n- 合併前：`code-review-and-quality`\n- 上線前觀測：`observability-and-instrumentation`\n- 收尾文件：`documentation-and-adrs`\n- 發版：`shipping-and-launch`\n\n## 工具路由\n\n- 大 repo \u002F 省 token：優先 `Semble`\n- 快速頁面驗證：優先 `agent-browser`\n- 可重現瀏覽器流程：優先 `playwright-cli`\n- 低 token MCP 探查：優先 `mcp-cli`\n- 沒有外部工具時，退回平台原生工具\n\n## 子代理\n\n- 平台支援 subagents 時，預設可自動分派\n- 角色看 `docs\u002Fsubagent_dispatch.md`\n- 不支援時，改為單代理順序執行\n\n## 停止條件\n\n只有以下情況才停：\n\n- 缺憑證、權限、付款、登入\n- 需要使用者做不可逆選擇\n- 外部服務不可用且無替代方案\n- 同一錯誤連修 3 次仍失敗\n\n## 自治等級\n\n- 預設 `L1 report-only`\n- 有 verifier 才升 `L2`\n- 有 scope \u002F budget \u002F audit 才升 `L3`\n\n## 規則\n\n- 不吹噓未驗證能力\n- 不假設所有平台都支援同一套 MCP \u002F subagents\n- 高風險決策採保守可逆預設，並寫入 `docs\u002FADRS.md`\n- 沒有驗證，不算完成\n","# loop-engineering\n\n本 skill 是專案主工作流。\n\n## 讀取順序\n\n1. `AGENTS.md`\n2. `docs\u002Fsession_loop_contract.md`\n3. `docs\u002Finteractive_project_flow.md`\n4. `docs\u002Fproject_architecture_best_practices.md`\n5. `docs\u002Fproject_lifecycle_automation.md`\n6. `docs\u002Fsubagent_dispatch.md`\n\n## 兩種模式\n\n### A. 新專案\n\n1. 必要時先用 `interview-me`\n2. 用 `idea-refine` 收斂想法\n3. 用 `spec-driven-development` 建 spec\n4. 技術棧定了就先用 `project-config-generation`\n5. 用 `planning-and-task-breakdown` 切 task\n6. 再進實作 loop\n\n### B. 舊專案改善\n\n1. 先看入口檔、設定、測試、部署\n2. 先提改善與重構切片\n3. 使用者確認後才做大改\n\n## 預設流程\n\n這是預設路徑，不是固定步數。\n\n1. 先判斷現在是新專案還是舊專案\n2. 只問 1-3 組決策題\n3. 先跑 `node scripts\u002Finspect_agent_capabilities.js`\n4. 先讀：\n   - `docs\u002Floop_maturity_model.md`\n   - `docs\u002Fengineering_phase_loop.md`\n   - `docs\u002Floop_circuit_breaker.md`\n5. 根據情境讀：\n   - `prompts\u002Finteractive_tech_stack_prompt.md`\n   - `prompts\u002Finteractive_api_key_prompt.md`\n   - `prompts\u002Flegacy_project_improvement_prompt.md`\n6. 若缺 `.loop\u002F*`，先用 `goal-loop` 或 `node scripts\u002Finit_session_loop.js . --goal \"\u003Cobjective>\"`\n7. 技術棧確認後，先用 `project-config-generation` 落設定檔\n8. 先給短版方案\n9. 視任務大小決定：\n   - 小任務：直接切 task 開工\n   - 中大型任務：再補完整計畫與 task 切片\n10. 完成必要確認後，進入 build-test-fix-doc loop\n11. 每輪記錄 `maturity_level`、`retry_count`、`blocked_reason`、`convergence_state`\n12. 若是 JS \u002F TS 專案且有 Biome，啟用 quality loop：\n    - `npx @biomejs\u002Fbiome check --write \u003Cchanged-paths>`\n    - 必要時再跑測試\n13. 進 merge \u002F ship 前補：\n    - `code-review-and-quality`\n    - `observability-and-instrumentation`\n    - `shipping-and-launch`\n\n## 初始化\n\n若是新專案或缺少核心檔案，先執行：\n\n```bash\nnode scripts\u002Finit_project_workspace.js \u003CtargetDir> --name \u003CprojectName> --idea \"\u003Cidea>\"\n```\n\n再依情境推薦 skills \u002F tools：\n\n```bash\nnode scripts\u002Fauto_skill_setup.js --project-type \u003Ctype> --ui-style \u003Cstyle> --deployment \u003Ctarget> --language \u003Clang> --database \u003Cdb>\n```\n\n## 實作 loop\n\n每輪都做：\n\n1. 選一個最小 task\n2. 最小必要修改\n3. 跑對應驗證\n4. 失敗就修根因\n5. 看 circuit breaker 是否該停\n6. 更新：\n   - `.loop\u002FPLAN.md`\n   - `.loop\u002FSTATE.json`\n   - `.loop\u002FCHECKPOINTS.md`\n   - `.loop\u002FEVIDENCE.md`\n   - 必要時記 `tier`、`orientation`、`time_budget`\n7. 若流程穩定可重用，參考 `docs\u002Fskill_crystallization_loop.md`\n8. 更新：\n   - `docs\u002FTASKS.md`\n   - `docs\u002FDEBUG_NOTES.md`\n   - `docs\u002FSTATE.md`\n   - `README.md`\n\n## 技能路由\n\n- 想法模糊：`idea-refine`\n- 要 `\u002Fgoal` 類跨平台 loop：`goal-loop`\n- 缺 spec：`spec-driven-development`\n- 工作太大：`planning-and-task-breakdown`\n- 技術棧已定但設定檔未落地：`project-config-generation`\n- 開始實作：`incremental-implementation`\n- 行為變動：`test-driven-development`\n- framework 問題：`source-driven-development`\n- 前端：`frontend-ui-engineering`\n- API 邊界：`api-and-interface-design`\n- runtime 驗證：`browser-testing-with-devtools`\n- 除錯：`debugging-and-error-recovery`\n- JS \u002F TS 品質 loop：`biome-quality-automation`\n- 合併前：`code-review-and-quality`\n- 上線前觀測：`observability-and-instrumentation`\n- 收尾文件：`documentation-and-adrs`\n- 發版：`shipping-and-launch`\n\n## 工具路由\n\n- 大 repo \u002F 省 token：優先 `Semble`\n- 快速頁面驗證：優先 `agent-browser`\n- 可重現瀏覽器流程：優先 `playwright-cli`\n- 低 token MCP 探查：優先 `mcp-cli`\n- 沒有外部工具時，退回平台原生工具\n\n## 子代理\n\n- 平台支援 subagents 時，預設可自動分派\n- 角色看 `docs\u002Fsubagent_dispatch.md`\n- 不支援時，改為單代理順序執行\n\n## 停止條件\n\n只有以下情況才停：\n\n- 缺憑證、權限、付款、登入\n- 需要使用者做不可逆選擇\n- 外部服務不可用且無替代方案\n- 同一錯誤連修 3 次仍失敗\n\n## 自治等級\n\n- 預設 `L1 report-only`\n- 有 verifier 才升 `L2`\n- 有 scope \u002F budget \u002F audit 才升 `L3`\n\n## 規則\n\n- 不吹噓未驗證能力\n- 不假設所有平台都支援同一套 MCP \u002F subagents\n- 高風險決策採保守可逆預設，並寫入 `docs\u002FADRS.md`\n- 沒有驗證，不算完成\n",{"name":5,"description":7},"claude\u002Fone-button-done-project-8xz5ky","15c2ed9e7009ccab2d9eb58840d76e13750d00ae",".agents\u002Fskills\u002Floop-engineering","https:\u002F\u002Fgithub.com\u002FNoMoneyDaddy\u002Fdemo-app","https:\u002F\u002Fgithub.com\u002FNoMoneyDaddy","2026-06-26 23:04:48",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add NoMoneyDaddy\u002Fdemo-app --skill loop-engineering",{"tool":36,"command":37},"bunx","bunx skills add NoMoneyDaddy\u002Fdemo-app --skill loop-engineering",{"tool":39,"command":40},"pnpm","pnpm dlx skills add NoMoneyDaddy\u002Fdemo-app --skill loop-engineering","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FNoMoneyDaddy\u002Fdemo-app\u002Fblob\u002Fclaude\u002Fone-button-done-project-8xz5ky\u002F.agents\u002Fskills\u002Floop-engineering\u002FSKILL.md",true,[],[45,52,59,66,73,80],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":19},"01M77PV8GM0F9FQ0HAHD8VC565","website-best-practices","Build websites with strong semantic HTML, accessibility, performance, content structure.","https:\u002F\u002Fgithub.com\u002FNoMoneyDaddy\u002Fdemo-app\u002Fblob\u002Fclaude\u002Fone-button-done-project-8xz5ky\u002Fskills\u002Fwebsite-best-practices\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M77PV6E2YD3NB3MJF1S0H65J","using-agent-skills","Meta skill entrypoint. Select the right workflow skill for the current project phase, initialize required docs, and keep execution aligned with the project lifecycle.","https:\u002F\u002Fgithub.com\u002FNoMoneyDaddy\u002Fdemo-app\u002Fblob\u002Fclaude\u002Fone-button-done-project-8xz5ky\u002Fskills\u002Fusing-agent-skills\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M77PV3B374HPTS05GSJVPP6A","ui-ux-designer","Create interface designs, design systems, and UX improvements with accessibility-first guidance.","https:\u002F\u002Fgithub.com\u002FNoMoneyDaddy\u002Fdemo-app\u002Fblob\u002Fclaude\u002Fone-button-done-project-8xz5ky\u002Fskills\u002Fui-ux-designer\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M77PV19MQ1WSV8GB7ZPZ63TA","typescript-best-practices","Apply TypeScript best practices for strict mode, safe narrowing, tsconfig safety, robust error handling.","https:\u002F\u002Fgithub.com\u002FNoMoneyDaddy\u002Fdemo-app\u002Fblob\u002Fclaude\u002Fone-button-done-project-8xz5ky\u002Fskills\u002Ftypescript-best-practices\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M77PTYWHB8CK99KAW2SGQBH0","tool-discovery-and-installation","Detect missing skills, MCP servers, CLIs, and sandbox tools; choose safe install paths; install or guide tool setup with explicit authorization and verification.","https:\u002F\u002Fgithub.com\u002FNoMoneyDaddy\u002Fdemo-app\u002Fblob\u002Fclaude\u002Fone-button-done-project-8xz5ky\u002Fskills\u002Ftool-discovery-and-installation\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M77PTWHE1EA7YSFGZ4EW9ANA","text-to-lottie","Generate or refine production-ready Lottie animations for web and app UI work.","https:\u002F\u002Fgithub.com\u002FNoMoneyDaddy\u002Fdemo-app\u002Fblob\u002Fclaude\u002Fone-button-done-project-8xz5ky\u002Fskills\u002Ftext-to-lottie\u002FSKILL.md",[],[]]